ppo-Huggy / run_logs /timers.json
Pandita-IA's picture
Huggy
b60bac9 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015650749206543,
"min": 1.4015650749206543,
"max": 1.424270749092102,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70184.7734375,
"min": 69175.828125,
"max": 77124.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.47932618683002,
"min": 75.47932618683002,
"max": 393.4609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49288.0,
"min": 48873.0,
"max": 50363.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999929.0,
"min": 49741.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999929.0,
"min": 49741.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.433746814727783,
"min": 0.07436762750148773,
"max": 2.5080835819244385,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1589.2366943359375,
"min": 9.44468879699707,
"max": 1589.2366943359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7921802353165233,
"min": 1.8526625591000234,
"max": 4.065682426195017,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2476.2936936616898,
"min": 235.28814500570297,
"max": 2476.2936936616898,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7921802353165233,
"min": 1.8526625591000234,
"max": 4.065682426195017,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2476.2936936616898,
"min": 235.28814500570297,
"max": 2476.2936936616898,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018111212296773576,
"min": 0.013376084301368489,
"max": 0.019582488592520046,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054333636890320725,
"min": 0.026752168602736978,
"max": 0.057005120854591945,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0574537461416589,
"min": 0.021996019687503577,
"max": 0.06045099000136058,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1723612384249767,
"min": 0.043992039375007154,
"max": 0.18135297000408174,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6764487745500058e-06,
"min": 3.6764487745500058e-06,
"max": 0.0002953125765624749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1029346323650017e-05,
"min": 1.1029346323650017e-05,
"max": 0.0008440824186391999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122545000000001,
"min": 0.10122545000000001,
"max": 0.198437525,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30367635000000004,
"min": 0.20759265000000005,
"max": 0.5813608000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.11499550000001e-05,
"min": 7.11499550000001e-05,
"max": 0.004922032497500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021344986500000033,
"min": 0.00021344986500000033,
"max": 0.014069903919999998,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1718972440",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718974994"
},
"total": 2554.131401273,
"count": 1,
"self": 0.4961304880002899,
"children": {
"run_training.setup": {
"total": 0.08700047700000368,
"count": 1,
"self": 0.08700047700000368
},
"TrainerController.start_learning": {
"total": 2553.5482703079997,
"count": 1,
"self": 4.572776049908498,
"children": {
"TrainerController._reset_env": {
"total": 3.447439255000006,
"count": 1,
"self": 3.447439255000006
},
"TrainerController.advance": {
"total": 2545.4085567520906,
"count": 232574,
"self": 5.005359196080917,
"children": {
"env_step": {
"total": 2022.1215278739908,
"count": 232574,
"self": 1668.5521379430304,
"children": {
"SubprocessEnvManager._take_step": {
"total": 350.4975358170124,
"count": 232574,
"self": 17.835019620071876,
"children": {
"TorchPolicy.evaluate": {
"total": 332.66251619694054,
"count": 222910,
"self": 332.66251619694054
}
}
},
"workers": {
"total": 3.07185411394795,
"count": 232574,
"self": 0.0,
"children": {
"worker_root": {
"total": 2546.0012967640077,
"count": 232574,
"is_parallel": true,
"self": 1202.4169576050917,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001149548999990202,
"count": 1,
"is_parallel": true,
"self": 0.000301945000046544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000847603999943658,
"count": 2,
"is_parallel": true,
"self": 0.000847603999943658
}
}
},
"UnityEnvironment.step": {
"total": 0.030584001000022454,
"count": 1,
"is_parallel": true,
"self": 0.0003863450000949342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000215017999948941,
"count": 1,
"is_parallel": true,
"self": 0.000215017999948941
},
"communicator.exchange": {
"total": 0.029222666999999092,
"count": 1,
"is_parallel": true,
"self": 0.029222666999999092
},
"steps_from_proto": {
"total": 0.0007599709999794868,
"count": 1,
"is_parallel": true,
"self": 0.00020559699999012082,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000554373999989366,
"count": 2,
"is_parallel": true,
"self": 0.000554373999989366
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1343.584339158916,
"count": 232573,
"is_parallel": true,
"self": 40.57548863389388,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.84706427503181,
"count": 232573,
"is_parallel": true,
"self": 86.84706427503181
},
"communicator.exchange": {
"total": 1123.0830960100304,
"count": 232573,
"is_parallel": true,
"self": 1123.0830960100304
},
"steps_from_proto": {
"total": 93.07869023995977,
"count": 232573,
"is_parallel": true,
"self": 34.86588182092652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.21280841903325,
"count": 465146,
"is_parallel": true,
"self": 58.21280841903325
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.2816696820189,
"count": 232574,
"self": 6.767508165945287,
"children": {
"process_trajectory": {
"total": 165.95285543007247,
"count": 232574,
"self": 164.5889154590721,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3639399710003772,
"count": 10,
"self": 1.3639399710003772
}
}
},
"_update_policy": {
"total": 345.56130608600114,
"count": 97,
"self": 279.7113974430016,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.84990864299954,
"count": 2910,
"self": 65.84990864299954
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.680002222012263e-07,
"count": 1,
"self": 9.680002222012263e-07
},
"TrainerController._save_models": {
"total": 0.11949728300032803,
"count": 1,
"self": 0.0018309170000065933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11766636600032143,
"count": 1,
"self": 0.11766636600032143
}
}
}
}
}
}
}